cloud-fan commented on a change in pull request #29999:
URL: https://github.com/apache/spark/pull/29999#discussion_r524214644
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/regexpExpressions.scala
##########
@@ -178,6 +180,90 @@ case class Like(left: Expression, right: Expression,
escapeChar: Char)
}
}
+/**
+ * Optimized version of LIKE ALL, when all pattern values are literal.
+ */
+abstract class LikeAllBase extends UnaryExpression with ImplicitCastInputTypes
with NullIntolerant {
+
+ protected def patterns: Seq[UTF8String]
+
+ protected def isNotDefined: Boolean
+
+ override def inputTypes: Seq[DataType] = StringType :: Nil
+
+ override def dataType: DataType = BooleanType
+
+ override def nullable: Boolean = true
+
+ private lazy val hasNull: Boolean = patterns.contains(null)
+
+ private lazy val cache = patterns.filterNot(_ == null)
+ .map(s => Pattern.compile(StringUtils.escapeLikeRegex(s.toString, '\\')))
+
+ override def eval(input: InternalRow): Any = {
+ val exprValue = child.eval(input)
+ if (exprValue == null) {
+ null
+ } else {
+ val allMatched = if (isNotDefined) {
+ !cache.exists(p => p.matcher(exprValue.toString).matches())
+ } else {
+ cache.forall(p => p.matcher(exprValue.toString).matches())
+ }
+ if (allMatched && hasNull) {
+ null
+ } else {
+ allMatched
+ }
+ }
+ }
+
+ override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = {
+ val eval = child.genCode(ctx)
+ val patternClass = classOf[Pattern].getName
+ val javaDataType = CodeGenerator.javaType(child.dataType)
+ val pattern = ctx.freshName("pattern")
+ val allMatched = ctx.freshName("allMatched")
+ val valueIsNull = ctx.freshName("valueIsNull")
+ val valueArg = ctx.freshName("valueArg")
+ val patternHasNull = ctx.addReferenceObj("hasNull", hasNull)
Review comment:
It's a boolean contant. We can change the generated code based on it.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
